We present SMURF, a method for unsupervised learning of optical flow that improves state of the art on all benchmarks by 36% to 40% (over the prior best method UFlow) and even outperforms several supervised approaches such as PWC-Net and FlowNet2. Our method integrates architecture improvements from supervised optical flow, i.e. the RAFT model, with new ideas for unsupervised learning that include a sequence-aware self-supervision loss, a technique for handling out-of-frame motion, and an approach for learning effectively from multi-frame video data while still only requiring two frames for inference.
Current benchmarks for optical flow algorithms evaluate the estimation quality by comparing their predicted flow field with the ground truth, and additionally may compare interpolated frames, based on these predictions, with the correct frames from the actual image sequences. For the latter comparisons, objective measures such as mean square errors are applied. However, for applications like image interpolation, the expected user's quality of experience cannot be fully deduced from such simple quality measures. Therefore, we conducted a subjective quality assessment study by crowdsourcing for the interpolated images provided in one of the optical flow benchmarks, the Middlebury benchmark. We used paired comparisons with forced choice and reconstructed absolute quality scale values according to Thurstone's model using the classical least squares method. The results give rise to a re-ranking of 141 participating algorithms w.r.t. visual quality of interpolated frames mostly based on optical flow estimation. Our re-ranking result shows the necessity of visual quality assessment as another evaluation metric for optical flow and frame interpolation benchmarks.Index Terms-visual quality assessment, optical flow, frame interpolation
ElsevierGasque Albalate, M.; González Altozano, P.; Maurer, D.; Moncho Esteve, IJ.; Gutiérrez-Colomer, RP.; Palau-Salvador, G.; García-Mari, E. (2015). Study of the influence of inner lining material on thermal stratification in a hot water storage tank. Applied Thermal Engineering. 75:344-356. doi:10.1016Engineering. 75:344-356. doi:10. /j.applthermaleng.2014
ABSTRACTThe present study has analyzed the influence of thermal conductivity of the inner lining material on the stratification process in a hot water tank during thermal charge and the later standby period. This analysis has been carried out numerically by a three-dimensional Computational Fluid Dynamics (CFD) model. Experimental measurements of temperature profiles are used to select and verificate the model, and to later validate CFD simulations. With the validated model, temperature over time at several heights, temperature profiles, velocity contours, water streamtraces and temperature contours, are studied and compared for three different inner lining materials. The obtained results confirm that a weak conducting lining material favours energy storage in the tank and the thermal stratification of water during charge and subsequent standby period. The effect of the inner lining material on the energy accumulated in water and on the moment of energy (stratification) is potentially enhanced when the material's thermal conductivity diminishes. The use of insulating paints as inner lining for water storage tanks could be a possible solution to be studied and subsequently adopted in practice to improve the efficient use of energy in stored water. The analysis 2 techniques employed prove most useful and enable the results to be compared and presented in a novel way.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.